Modeling video activity with dynamic phrases and its application to action recognition in tennis videos

Vainstein, Jonathan; Manera, José; Negri, Pablo; Delrieux, Claudio; Maguitman, Ana

Modeling video activity with dynamic phrases and its application to action recognition in tennis videos, (2014)

Vainstein, Jonathan; Manera, José; Negri, Pablo; Delrieux, Claudio; Maguitman, Ana

Instituto: Instituto de Tecnología
Temas: Reconocimiento de Acciones; Descripción de Movimiento; Deportes; Tenis
Extensión: 2 p.
Area de investigación: Informática / Telecomunicaciones / Electrónica
Línea de investigación: Procesamiento de Imágenes
Responsable del proyecto: Negri, Pablo
Nombre del proyecto: Reconocimiento y Análisis de Acciones en Videos
Código del proyecto: A14T24

Resumen:

We present a novel approach to action recognition in tennis shot sequences. The underlying model considers the per-frame motion to be regarded as a word (within an alphabet of possible motions), and the sequence of frames as a phrase whose meaning is determined by the words given in a specific order.

Descripción:

Vainstein J., Manera J.F., Negri P., Delrieux C., Maguitman A. (2014) Modeling Video Activity with Dynamic Phrases and Its Application to Action Recognition in Tennis Videos. In: Bayro-Corrochano E., Hancock E. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2014. Lecture Notes in Computer Science, vol 8827. Springer, Cham. https://doi.org/10.1007/978-3-319-12568-8_110

Mostrar el registro completo del ítem